© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76284
    Prev
    Next
    INDEX
    Explanations

    privacy and integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     აღმასრულებელი
    0.41
    จุบัน
    0.39
    algèbre
    0.38
     Algar
    0.38
    坆
    0.37
     rek
    0.36
     WARRANTIES
    0.36
    刮
    0.35
     recib
    0.35
    ____________
    0.35
    POSITIVE LOGITS
    strength
    0.39
    uva
    0.38
     burners
    0.38
     Iw
    0.38
     strength
    0.37
     Impossible
    0.36
    Iw
    0.36
     Listen
    0.36
     suspicious
    0.36
     Living
    0.35
    Activations Density 0.037%

    No Known Activations